Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 14, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

A deep learning architecture for metabolic pathway prediction.

Mayank Baranwal1, Abram Magner2, Paolo Elvati3

  • 1Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48109, USA.

Bioinformatics (Oxford, England)
|July 13, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Universal feature selection for simultaneous interpretability of multitask datasets.

Journal of cheminformatics·2026
Same author

A Practical Approach to Disease Risk Prediction: Focus on High-Risk Patients via Highest-<i>k</i> Loss.

Proceedings. IEEE International Conference on Bioinformatics and Biomedicine·2025
Same author

Can Machine Learning Overcome the 95% Failure Rate and Reality that Only 30% of Approved Cancer Drugs Meaningfully Extend Patient Survival?

Journal of medicinal chemistry·2024
Same author

Unifying structural descriptors for biological and bioinspired nanoscale complexes.

Nature computational science·2024
Same author

Domain-agnostic predictions of nanoscale interactions in proteins and nanoparticles.

Nature computational science·2024
Same author

Finite-size effects in the static structure factor S(k) and S(0) for a two-dimensional Yukawa liquid.

Physical review. E·2023

This study introduces a novel machine learning method for predicting metabolic pathway classes of compounds. The approach achieves high accuracy, outperforming existing methods in classifying both single and multiple pathway memberships.

Area of Science:

  • Biochemistry
  • Computational Chemistry
  • Machine Learning

Background:

  • Predicting metabolic pathway classes is crucial for designing synthetic reactions.
  • Understanding molecular structure-pathway relationships aids in new molecule synthesis.
  • Biochemical compounds participate in specific metabolic pathways within cells.

Purpose of the Study:

  • To develop a machine learning framework for predicting metabolic pathway classes of biochemical compounds.
  • To automatically extract molecular shape features from SMILES representations.
  • To improve the accuracy of metabolic pathway prediction compared to existing methods.

Main Methods:

  • A hybrid machine learning approach combining graph convolutional networks and random forest classifiers.

More Related Videos

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jul 14, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

  • Graph convolutional networks extract molecular shape features from SMILES strings.
  • Random forest classifier predicts pathway classes based on extracted features.

    • Main Results:

    • Achieved 95.16% accuracy in predicting metabolic pathway classes, surpassing competing methods (84.92% or less).
    • Demonstrated high prediction accuracy (95.62%) for compounds with mixed membership in multiple pathway classes (multi-label task).
    • Showcased that linear/logistic regression models can predict global physicochemical features from extracted shape features.

    Conclusions:

    • The developed hybrid machine learning framework accurately predicts metabolic pathway classes.
    • The method effectively handles both single and multi-label classification tasks.
    • The approach offers a significant advancement in computational prediction for molecular synthesis and pathway analysis.